© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3264
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and symbols that seem to be related to technical data or code

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values and symbols related to ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diagn
    -0.77
     astroph
    -0.77
     handic
    -0.70
     undert
    -0.69
    én
    -0.66
     Astron
    -0.65
     surve
    -0.63
     Tec
    -0.63
     AST
    -0.62
     unders
    -0.62
    POSITIVE LOGITS
    2
    1.37
     2
    1.10
    3
    1.00
    ãĤ°
    0.97
    ²
    0.91
    1
    0.89
    ĩ
    0.88
    II
    0.86
    Dual
    0.85
    ĥ
    0.83
    Activations Density 0.174%

    No Known Activations